© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 26878
    Prev
    Next
    INDEX
    Explanations

    references to historical persecution and the consequences of inaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aras
    -0.08
    aza
    -0.07
    anela
    -0.07
    ulta
    -0.07
    okie
    -0.07
    ccoli
    -0.07
    ayet
    -0.07
    atori
    -0.07
    leta
    -0.07
    üle
    -0.07
    POSITIVE LOGITS
     Caldwell
    0.06
    (mapped
    0.06
     masse
    0.06
    InProgress
    0.06
     krit
    0.06
     Arthur
    0.06
    ë¸
    0.06
    .matcher
    0.06
    _ASSUME
    0.06
    avel
    0.05
    Activations Density 0.007%

    No Known Activations